Few-shot Learning for Multi-modal Social Media Event Filtering

Autor(es)

Nascimento, Jose ; Cardenuto, Joao Phillipe ; Yang, Jing ; Rocha, Anderson ; IEEE

• Tipo de documento: Artigo Científico
• Fonte: 2022 IEEE INTERNATIONAL WORKSHOP ON INFORMATION FORENSICS AND SECURITY (WIFS); v. N/A, p. 6-pg., 2022-01-01.

Resumo

Social media has become an important data source for event analysis. When collecting this type of data, most contain no useful information to a target event. Thus, it is essential to filter out those noisy data at the earliest opportunity for a human expert to perform further inspection. Most existing solutions for event filtering rely on fully supervised methods for training. However, in many real-world scenarios, having access to large number of labeled samples is not possible. To deal with a few labeled sample training problem for event filtering, we propose a graph-based few-shot learning pipeline. We also release the Brazilian Protest Dataset to test our method. To the best of our knowledge, this dataset is the first of its kind in event filtering that focuses on protests in multi-modal social media data, with most of the text in Portuguese. Our experimental results show that our proposed pipeline has comparable performance with only a few labeled samples (60) compared with a fully labeled dataset (3100). To facilitate the research community, we make our dataset and code available at https://github.com/jdnascim/7Set-AL. (AU)

• Processo FAPESP: 17/12646-3 - Déjà vu: coerência temporal, espacial e de caracterização de dados heterogêneos para análise e interpretação de integridade
• Beneficiário: Anderson de Rezende Rocha
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 20/02241-9 - Reconhecimento de padrões e detecção de subeventos de destaque em dados de fontes heterogêneas
• Beneficiário: José Dorivaldo Nascimento Souza Júnior
• Modalidade de apoio: Bolsas no Brasil - Doutorado Direto
• Processo FAPESP: 20/02211-2 - Filtragem e análise de proveniência
• Beneficiário: João Phillipe Cardenuto
• Modalidade de apoio: Bolsas no Brasil - Doutorado Direto
• Processo FAPESP: 19/04053-8 - Reconstrução de eventos a partir de dados visuais heterogêneos
• Beneficiário: Jing Yang
• Modalidade de apoio: Bolsas no Brasil - Doutorado